def handle_pdf(self, url, content):
sample = log.ThugLogging.build_sample(content, url)
if sample is None or sample['type'] not in ('PDF', ):
return
fd, rfile = tempfile.mkstemp()
with open(rfile, 'wb') as fd:
fd.write(content)
pdfparser = PDFParser()
try:
ret, pdf = pdfparser.parse(rfile, forceMode=True, looseMode=True)
except:
os.remove(rfile)
return False
statsDict = pdf.getStats()
analysis = self.getPeepXML(statsDict, url)
log_dir = os.path.join(log.ThugLogging.baseDir, "analysis", "pdf")
log.ThugLogging.log_peepdf(log_dir, sample, analysis)
self.swf_mastah(pdf, statsDict, url)
os.remove(rfile)
return True
def handle_pdf(self, url, content):
sample = log.ThugLogging.build_sample(content, url)
if sample is None or sample['type'] not in ('PDF', ):
return
fd, rfile = tempfile.mkstemp()
with open(rfile, 'wb') as fd:
fd.write(content)
pdfparser = PDFParser()
try:
ret, pdf = pdfparser.parse(rfile, forceMode = True, looseMode = True) #pylint:disable=unused-variable
except: #pylint:disable=bare-except
os.remove(rfile)
return False
statsDict = pdf.getStats()
analysis = self.getPeepXML(statsDict, url)
log_dir = os.path.join(log.ThugLogging.baseDir, "analysis", "pdf")
log.ThugLogging.log_peepdf(log_dir, sample, analysis)
self.swf_mastah(pdf, statsDict, url)
os.remove(rfile)
return True
def handle_pdf(self, url, content):
m = hashlib.md5()
m.update(content)
md5sum = m.hexdigest()
rfile = log.ThugLogging.store_content(log.ThugLogging.baseDir, md5sum, content)
pdfparser = PDFParser()
try:
ret, pdf = pdfparser.parse(rfile, forceMode = True, looseMode = True)
except:
os.remove(rfile)
return False
statsDict = pdf.getStats()
analysis = self.getPeepXML(statsDict, url)
pdflogdir = os.path.join(log.ThugLogging.baseDir, "analysis", "pdf")
try:
os.makedirs(pdflogdir)
except:
pass
log.ThugLogging.store_content(pdflogdir, "%s.xml" % (statsDict["MD5"], ), analysis)
self.swf_mastah(pdf, statsDict)
os.remove(rfile)
return True